Zemin Su

Big Data, Predictive Analytics, and Quality Improvement in Kidney Transplantation: A Proof of Concept

We sought proof of concept of a Big Data Solution incorporating longitudinal structured and unstructured patient‐level data from electronic health records (EHR) to predict graft loss (GL) and mortality. For a quality improvement initiative, GL and mortality prediction models were constructed using baseline and follow‐up data (0–90 days posttransplant; structured and unstructured for 1‐year models; data up to 1 year for 3‐year models) on adult solitary kidney transplant recipients transplanted during 2007–2015 as follows: Model 1: United Network for Organ Sharing (UNOS) data; Model 2: UNOS & Transplant Database (Tx Database) data; Model 3: UNOS, Tx Database & EHR comorbidity data; and Model 4: UNOS, Tx Database, EHR data, Posttransplant trajectory data, and unstructured data. A 10% 3‐year GL rate was observed among 891 patients (2007–2015). Layering of data sources improved model performance; Model 1: area under the curve (AUC), 0.66; (95% confidence interval [CI]: 0.60, 0.72); Model 2: AUC, 0.68; (95% CI: 0.61–0.74); Model 3: AUC, 0.72; (95% CI: 0.66–077); Model 4: AUC, 0.84, (95 % CI: 0.79–0.89). One‐year GL (AUC, 0.87; Model 4) and 3‐year mortality (AUC, 0.84; Model 4) models performed similarly. A Big Data approach significantly adds efficacy to GL and mortality prediction models and is EHR deployable to optimize outcomes.

Tacrolimus Trough Concentration Variability and Disparities in African American Kidney Transplantation

Background Low tacrolimus concentrations have been associated with higher risk of acute rejection, particularly within African American (AA) kidney transplant recipients; little is known about intrapatient tacrolimus variabilities impact on racial disparities. Methods Ten year, single-center, longitudinal cohort study of kidney recipients. Intrapatient tacrolimus variability was assessed using the coefficient of variation (CV) measured between 1 month posttransplant and the clinical event, with a comparable period assessed in those without events. Pediatrics, nontacrolimus/mycophenolate regimens, and nonrenal transplants were excluded. Multivariable Cox regression models were used to analyze data. Results One thousand four hundred eleven recipients were included (54.4% AA) with 39 521 concentrations used to assess intrapatient tacrolimus CV. Overall, intrapatient tacrolimus CV was higher in AAs versus non-AAs (39.9 ± 19.8 % vs 34.8 ± 15.8% P < 0.001). Tacrolimus variability was a significant risk factor for deleterious clinical outcomes. A 10% increase in tacrolimus CV augmented the risk of acute rejection by 20% (adjusted hazard ratio, 1.20, 1.13-1.28; P < 0.001) and the risk of graft loss by 30% (adjusted hazard ratio, 1.30, 1.23-1.37; P < 0.001), with significant effect modification by race for acute rejection, but not graft loss. High tacrolimus variability (CV >40%) was a significant explanatory variable for disparities in AAs; the crude relative risk of acute rejection in AAs was reduced by 46% when including tacrolimus variability in modeling and reduced by 40% for graft loss. Conclusions These data demonstrate that intrapatient tacrolimus variability is strongly associated with acute rejection in AAs and graft loss in all patients. Tacrolimus variability is a significant explanatory variable for disparities in AA recipients.

A Comprehensive View of Frequent Emergency Department Users Based on Data from a Regional HIE.

Objectives A small but significant number of patients make frequent emergency department (ED) visits to multiple EDs within a region. We have a unique health information exchange (HIE) that includes every ED encounter in all hospital systems in our region. Using our HIE we were able to characterize all frequent ED users in our region, regardless of hospital visited or payer class. The objective of our study was to use data from an HIE to characterize patients in a region who are frequent ED users (FEDUs). Methods We constructed a database from a cohort of adult patients (18 years old or older) with information in a regional HIE for a 1-year period beginning in April 2012. Patients were defined as FEDUs (those who made four or more visits during the study period) and non-FEDUs (those who made fewer than four ED visits during the study period). Predictor variables included age, race, sex, payer class, county of residence, and International Classification of Diseases, Ninth Revision codes. Bivariate (&khgr;2) and multivariate (logistic regression) analyses were performed to determine associations between predictor variables and the outcome of being a FEDU. Results The database contained 127,672 patients, 12,293 (9.6%) of whom were FEDUs. Logistic regression showed the following patient characteristics to be significantly associated with the outcome of being a FEDU: age 35 to 44 years; African American race; Medicaid, Medicare, and dual-pay payer class; and International Classification of Diseases, Ninth Revision codes 630 to 679 (complications of pregnancy, childbirth, and puerperium), 780 to 799 (ill-defined conditions), 280 to 289 (diseases of the blood), 290–319 (mental disorders), 680 to 709 (diseases of the skin and subcutaneous tissue), 710 to 739 (musculoskeletal and connective tissue disease), 460 to 519 (respiratory disease), and 520 to 579 (digestive disease). No significant differences were noted between men and women. Conclusions Data from an HIE can be used to describe all of the patients within a region who are FEDUs, regardless of the hospital system they visited. This information can be used to focus care coordination efforts and link appropriate patients to a medical home. Future studies can be designed to learn the reasons why patients become FEDUs, and interventions can be developed to address deficiencies in health care that result in frequent ED visits.

The impact of time-varying clinical surrogates on disparities in African-American kidney transplant recipients - a retrospective longitudinal cohort study

An improved understanding of the impact of clinical surrogates on disparities in African‐American (AA) kidney transplantation (KTX) is needed. We conducted a 10‐year retrospective longitudinal cohort study of electronically abstracted clinical data assessing the impact of surrogates on disparities in KTX. Clinical surrogates were assessed by posttransplant year (1, 2, 3 or 4) and defined as acute rejection (Banff ≥1A), mean SBP >140 mmHg, tacrolimus variability (CV) >40%, mean glucose >160 mg/dl and mean hemoglobin <10 g/dl. We utilized landmark methodology to minimize immortal time bias and logistic and survival regression to assess outcomes; 1610 KTX were assessed (54.2% AAs), with 1000, 468, 368 and 303 included in the year 1, 2, 3 and 4 complete case analyses, respectively. AAs had significantly higher odds of developing a clinical surrogate, which increased in posttransplant years three and four [OR year 1 1.99 (1.38–2.88), year 2 1.77 (1.20–2.62), year 3 2.35 (1.49–3.71), year 4 2.85 (1.72–4.70)]. Adjusting for the five clinical surrogates in survival models explained a significant portion of the higher risks of graft loss in AAs in post‐transplant years three and four. Results suggest focusing efforts on improving late clinical surrogate management within AAs may help mitigate racial disparities in KTX.

Development and future deployment of a five-year allograft survival model for kidney transplantation: Predicting graft survival in kidney transplant

Identifying kidney transplant patients at highest risk for graft loss prior to loss may allow for effective interventions to improve 5 years survival.

A quantitative appraisal of African Americans’ decisions to become registered organ donors at the driver’s license office

African American (AA) organ donation registration rates fall short of national objectives. The goal of the present study was to utilize data acquired from a quantitative telephone survey to provide information for a future Department of Motorized Vehicles (DMV) intervention to increase AA organ donor registration at the DMV. AAs (n = 20 177) that had visited an Alabama DMV office within a 3‐month period were recruited via direct mailing to participate in a quantitative phone survey. Data from 155 respondents that participated in the survey were analyzed. Of those respondents deciding to become a registered organ donor (ROD; n = 122), one‐third made that decision at the time of visiting the DMV. Of those who chose not to become a ROD (n = 33), one‐third made the decision during the DMV visit. Almost 85% of all participants wanted to learn more about organ donation while waiting at the DMV, preferably via TV messaging (digital signage), with the messaging delivered from organ donors, transplant recipients, and healthcare experts. Altruism, accurate organ donation information, and encouragement from family and friends were the most important educational topics to support AAs becoming a ROD. These data provide a platform to inform future interventions designed to increase AAs becoming a ROD at the DMV.

When Should ED Physicians Use an HIE? Predicting Presence of Patient Data in an HIE.

Objectives Health information exchanges (HIEs) make possible the construction of databases to characterize patients as multisystem users (MSUs), those visiting emergency departments (EDs) of more than one hospital system within a region during a 1-year period. HIE data can inform an algorithm highlighting patients for whom information is more likely to be present in the HIE, leading to a higher yield HIE experience for ED clinicians and incentivizing their adoption of HIE. Our objective was to describe patient characteristics that determine which ED patients are likely to be MSUs and therefore have information in an HIE, thereby improving the efficacy of HIE use and increasing ED clinician perception of HIE benefit. Methods Data were extracted from a regional HIE involving four hospital systems (11 EDs) in the Charleston, South Carolina area. We used univariate and multivariable regression analyses to develop a predictive model for MSU status. Results Factors associated with MSUs included younger age groups, dual-payer insurance status, living in counties that are more rural, and one of at least six specific diagnoses: mental disorders; symptoms, signs, and ill-defined conditions; complications of pregnancy, childbirth, and puerperium; diseases of the musculoskeletal system; injury and poisoning; and diseases of the blood and blood-forming organs. For patients with multiple ED visits during 1 year, 43.8% of MSUs had ≥4 visits, compared with 18.0% of non-MSUs (P < 0.0001). Conclusions This predictive model accurately identified patients cared for at multiple hospital systems and can be used to increase the likelihood that time spent logging on to the HIE will be a value-added effort for emergency physicians.